COVID-19 Analysis
Katie Forthman
Thu May 7 10:17:50 2020
Click here for interactive plots:
Click here to see how cities and counties overlap:
Compare COVID stats to Neighborhood Factors
data.cor <- cor(county.Demo_and_Covid.allcounties[,-1], use = "complete.obs", method = "spearman")
corrplot.mixed(data.cor, upper = 'ellipse', lower = 'number', tl.pos = 'lt', tl.cex = 1, lower.col = "black", number.cex = 0.5)
Compare COVID stats to 500 cities data and Neighborhood Factors
data.cor2 <- cor(county.Demo_and_Covid.500counties[,-c(1:2)], use = "complete.obs", method = "spearman")
corrplot.mixed(data.cor2, upper = 'ellipse', lower = 'number', tl.pos = 'lt', tl.cex = 1, lower.col = "black", number.cex = 0.5)
corrplot.mixed(data.cor2[7:13,c(1:5, 14:42,6)], upper = 'ellipse', tl.pos = 'lt', tl.cex = 1, lower.col = "black", number.cex = 0.5)
—-Linear Mixed Effects Model —-
this.lme <- lmer("total.cases.percap ~ Affluence + Singletons.in.Tract + Seniors.in.Tract + African.Americans.in.Tract + Noncitizens.in.Tract + High.BP + Binge.Drinking + Cancer + Asthma + Heart.Disease + COPD + Smoking + Diabetes + No.Physical.Activity + Obesity + Poor.Sleeping.Habits + Poor.Mental.Health + Testing_Rate + Hospitalization_Rate + (1 | stateID)", data = county.Demo_and_Covid.500counties)## Warning: Some predictor variables are on very different scales: consider
## rescaling
## Warning: Some predictor variables are on very different scales: consider
## rescalingprint(summary(this.lme), correlation=TRUE)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula:
## "total.cases.percap ~ Affluence + Singletons.in.Tract + Seniors.in.Tract + African.Americans.in.Tract + Noncitizens.in.Tract + High.BP + Binge.Drinking + Cancer + Asthma + Heart.Disease + COPD + Smoking + Diabetes + No.Physical.Activity + Obesity + Poor.Sleeping.Habits + Poor.Mental.Health + Testing_Rate + Hospitalization_Rate + (1 | stateID)"
## Data: county.Demo_and_Covid.500counties
##
## REML criterion at convergence: -1133.1
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -2.7870 -0.3388 -0.0848 0.1951 5.7214
##
## Random effects:
## Groups Name Variance Std.Dev.
## stateID (Intercept) 0.0000007916 0.0008897
## Residual 0.0000130205 0.0036084
## Number of obs: 169, groups: stateID, 32
##
## Fixed effects:
## Estimate Std. Error df
## (Intercept) -0.0082746977 0.0092482150 63.0405055855
## Affluence 0.0045143408 0.0010685088 90.7627502550
## Singletons.in.Tract 0.0016543371 0.0009304859 131.2345083517
## Seniors.in.Tract 0.0009547713 0.0012094606 141.6753743692
## African.Americans.in.Tract 0.0002478738 0.0010152953 143.6991673585
## Noncitizens.in.Tract 0.0008402504 0.0007498853 114.4243879231
## High.BP 0.0002272403 0.0001861718 86.0965242442
## Binge.Drinking 0.0001389002 0.0001495917 34.2791707145
## Cancer -0.0008345377 0.0010714213 84.3052078031
## Asthma 0.0004995414 0.0005219335 32.1209525041
## Heart.Disease 0.0006970758 0.0012481161 60.9114634260
## COPD -0.0000074504 0.0010550340 64.0181000174
## Smoking -0.0001364829 0.0002226376 67.8725308295
## Diabetes -0.0004725503 0.0005271498 65.5462685871
## No.Physical.Activity -0.0000057796 0.0001988679 75.2591710707
## Obesity 0.0002002965 0.0001707299 79.4812485173
## Poor.Sleeping.Habits -0.0000013822 0.0001645511 116.8142930114
## Poor.Mental.Health -0.0000003752 0.0003947858 26.0236345433
## Testing_Rate 0.0000004996 0.0000003168 28.7507897306
## Hospitalization_Rate -0.0001245472 0.0000862535 24.3916999506
## t value Pr(>|t|)
## (Intercept) -0.895 0.3743
## Affluence 4.225 0.0000568 ***
## Singletons.in.Tract 1.778 0.0777 .
## Seniors.in.Tract 0.789 0.4312
## African.Americans.in.Tract 0.244 0.8075
## Noncitizens.in.Tract 1.121 0.2648
## High.BP 1.221 0.2256
## Binge.Drinking 0.929 0.3596
## Cancer -0.779 0.4382
## Asthma 0.957 0.3457
## Heart.Disease 0.559 0.5785
## COPD -0.007 0.9944
## Smoking -0.613 0.5419
## Diabetes -0.896 0.3733
## No.Physical.Activity -0.029 0.9769
## Obesity 1.173 0.2442
## Poor.Sleeping.Habits -0.008 0.9933
## Poor.Mental.Health -0.001 0.9992
## Testing_Rate 1.577 0.1258
## Hospitalization_Rate -1.444 0.1615
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1##
## Correlation of fixed effects could have been required in summary()##
## Correlation of Fixed Effects:
## (Intr) Afflnc Sng..T Snr..T A.A..T Nnc..T Hgh.BP Bng.Dr Cancer
## Affluence 0.156
## Sngltns.n.T -0.006 0.048
## Snrs.n.Trct 0.588 0.379 0.171
## Afrcn.Am..T 0.192 0.162 -0.433 0.170
## Nnctzns.n.T -0.009 0.094 0.048 0.061 -0.075
## High.BP 0.018 0.247 0.094 0.135 -0.108 0.397
## Bing.Drnkng -0.246 -0.178 -0.302 -0.167 0.114 0.053 0.144
## Cancer -0.597 -0.215 0.182 -0.343 -0.081 -0.156 -0.398 -0.131
## Asthma -0.358 -0.215 -0.206 -0.167 0.075 0.086 0.168 -0.017 0.040
## Heart.Dises -0.147 0.079 -0.285 -0.149 0.237 -0.098 -0.031 0.063 -0.460
## COPD 0.553 0.039 0.133 0.271 0.008 0.289 0.213 0.122 -0.268
## Smoking -0.189 0.109 -0.180 -0.131 -0.084 -0.006 -0.107 -0.300 0.086
## Diabetes 0.058 -0.310 -0.160 -0.234 -0.273 -0.325 -0.528 0.039 0.221
## N.Physcl.Ac -0.180 -0.074 0.101 -0.032 -0.036 -0.233 -0.119 0.084 0.494
## Obesity 0.026 0.437 0.393 0.306 0.163 0.213 -0.070 -0.221 0.104
## Pr.Slpng.Hb -0.496 -0.414 0.182 -0.389 -0.404 0.006 -0.184 0.065 0.173
## Pr.Mntl.Hlt -0.317 0.263 -0.049 -0.054 0.109 -0.199 -0.092 0.047 0.310
## Testing_Rat 0.192 -0.082 -0.085 -0.006 0.065 -0.092 -0.021 0.020 -0.193
## Hsptlztn_Rt -0.132 -0.218 -0.156 -0.266 -0.074 -0.127 -0.140 -0.165 0.056
## Asthma Hrt.Ds COPD Smokng Diabts N.Ph.A Obesty Pr.S.H Pr.M.H
## Affluence
## Sngltns.n.T
## Snrs.n.Trct
## Afrcn.Am..T
## Nnctzns.n.T
## High.BP
## Bing.Drnkng
## Cancer
## Asthma
## Heart.Dises 0.274
## COPD -0.366 -0.565
## Smoking 0.076 0.220 -0.526
## Diabetes -0.121 -0.237 -0.159 0.289
## N.Physcl.Ac 0.013 -0.394 -0.001 -0.347 -0.087
## Obesity -0.286 -0.107 0.188 -0.217 -0.399 -0.061
## Pr.Slpng.Hb 0.082 0.243 -0.215 0.038 -0.018 -0.098 -0.172
## Pr.Mntl.Hlt -0.223 0.093 -0.457 0.076 0.032 0.078 0.093 -0.191
## Testing_Rat -0.354 -0.022 0.184 0.179 0.151 -0.329 0.078 -0.142 -0.128
## Hsptlztn_Rt 0.050 0.074 -0.106 0.149 0.124 -0.035 -0.118 0.009 -0.058
## Tstn_R
## Affluence
## Sngltns.n.T
## Snrs.n.Trct
## Afrcn.Am..T
## Nnctzns.n.T
## High.BP
## Bing.Drnkng
## Cancer
## Asthma
## Heart.Dises
## COPD
## Smoking
## Diabetes
## N.Physcl.Ac
## Obesity
## Pr.Slpng.Hb
## Pr.Mntl.Hlt
## Testing_Rat
## Hsptlztn_Rt 0.283
## fit warnings:
## Some predictor variables are on very different scales: consider rescalingTesting Rate
testing.data.state <- compiled.stats[[length(daily_filenames)]][, c("Province_State", "Testing_Rate")]
testing.data.state <- testing.data.state[!is.na(testing.data.state$Testing_Rate),]
testing.data.state <- testing.data.state[order(testing.data.state$Testing_Rate),]
col.state <- rep("pink", nrow(testing.data.state))
avg.test.rate <- mean(testing.data.state$Testing_Rate, na.rm = T)
col.state[testing.data.state$Testing_Rate < avg.test.rate] <- "grey"
col.state[testing.data.state$Province_State == "Oklahoma"] <- "lightblue"
par(mar = c(5,6,4,2))
barplot(testing.data.state$Testing_Rate, names.arg = testing.data.state$Province_State, horiz = T, main = "Testing Rate by State", las = 2, cex.axis = 1, cex.names = 0.5, col = col.state, border = F, xlab = "Total number of people tested per 100,000 persons.")
abline(v = avg.test.rate, col = "red")
text(x = avg.test.rate + 10, y = 1, labels = "Average Testing Rate", adj = c(0, 0.5), col = "red")
day.first.case <- min(which(US.total$cases.total > 100))
n.days <- nrow(US.total)
par(mar = c(5,5,4,2))
barplot(US.total$cases.total[day.first.case:n.days], main = "Total COVID-19 cases by Date in US", las = 2, cex.axis = 1, cex.names = 0.5)
barplot(US.total$cases.total[day.first.case:n.days], main = "Total COVID-19 cases by Date in US, log scale", las = 2, cex.axis = 1, cex.names = 0.5, log = "y")
barplot(US.total$deaths.total[day.first.case:n.days], main = "Total COVID-19 deaths by Date in US", las = 2, cex.axis = 1, cex.names = 0.5)
barplot(US.total$deaths.total[day.first.case:n.days], main = "Total COVID-19 deaths by Date in US, log scale", las = 2, cex.axis = 1, cex.names = 0.5, log = "y")
barplot(US.total$rise.cases.total[day.first.case:n.days], main = "Rise in Cases of COVID-19 by Date in US", las = 2, cex.axis = 1, cex.names = 0.5)
barplot(US.total$rise.deaths.total[day.first.case:n.days], main = "Rise in Deaths of COVID-19 by Date in US", las = 2, cex.axis = 1, cex.names = 0.5)